richpsharp commited on
Commit
55e0aac
1 Parent(s): 594da64

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,73 +1,38 @@
1
  {
2
- "_name_or_path": "google/flan-t5-small",
3
  "architectures": [
4
- "T5ForSequenceClassification"
5
  ],
6
- "classifier_dropout": 0.0,
7
- "d_ff": 1024,
8
- "d_kv": 64,
9
- "d_model": 512,
10
- "decoder_start_token_id": 0,
11
- "dense_act_fn": "gelu_new",
12
- "dropout_rate": 0.1,
13
- "eos_token_id": 1,
14
- "feed_forward_proj": "gated-gelu",
15
  "id2label": {
16
  "0": "LABEL_0",
17
  "1": "LABEL_1",
18
  "2": "LABEL_2"
19
  },
20
- "initializer_factor": 1.0,
21
- "is_encoder_decoder": true,
22
- "is_gated_act": true,
23
  "label2id": {
24
  "LABEL_0": 0,
25
  "LABEL_1": 1,
26
  "LABEL_2": 2
27
  },
28
- "layer_norm_epsilon": 1e-06,
29
- "model_type": "t5",
30
- "n_positions": 512,
31
- "num_decoder_layers": 8,
32
- "num_heads": 6,
33
- "num_layers": 8,
34
- "output_past": true,
35
- "pad_token_id": 0,
36
  "problem_type": "single_label_classification",
37
- "relative_attention_max_distance": 128,
38
- "relative_attention_num_buckets": 32,
39
- "task_specific_params": {
40
- "summarization": {
41
- "early_stopping": true,
42
- "length_penalty": 2.0,
43
- "max_length": 200,
44
- "min_length": 30,
45
- "no_repeat_ngram_size": 3,
46
- "num_beams": 4,
47
- "prefix": "summarize: "
48
- },
49
- "translation_en_to_de": {
50
- "early_stopping": true,
51
- "max_length": 300,
52
- "num_beams": 4,
53
- "prefix": "translate English to German: "
54
- },
55
- "translation_en_to_fr": {
56
- "early_stopping": true,
57
- "max_length": 300,
58
- "num_beams": 4,
59
- "prefix": "translate English to French: "
60
- },
61
- "translation_en_to_ro": {
62
- "early_stopping": true,
63
- "max_length": 300,
64
- "num_beams": 4,
65
- "prefix": "translate English to Romanian: "
66
- }
67
- },
68
- "tie_word_embeddings": false,
69
  "torch_dtype": "float32",
70
  "transformers_version": "4.33.3",
 
71
  "use_cache": true,
72
- "vocab_size": 32128
73
  }
 
1
  {
2
+ "_name_or_path": "roberta-base",
3
  "architectures": [
4
+ "RobertaForSequenceClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
 
 
13
  "id2label": {
14
  "0": "LABEL_0",
15
  "1": "LABEL_1",
16
  "2": "LABEL_2"
17
  },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
 
20
  "label2id": {
21
  "LABEL_0": 0,
22
  "LABEL_1": 1,
23
  "LABEL_2": 2
24
  },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "roberta",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
 
32
  "problem_type": "single_label_classification",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  "torch_dtype": "float32",
34
  "transformers_version": "4.33.3",
35
+ "type_vocab_size": 1,
36
  "use_cache": true,
37
+ "vocab_size": 50265
38
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47e0614df138ad0b5c4f17cd7911883a9a42f6cb54a50deb8c4842037d85b309
3
- size 243172494
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cc61e6490df922fb50e757ba551446e1a0d34e0bb44253e67fc1626b2b0142d
3
+ size 498661166
special_tokens_map.json CHANGED
@@ -1,107 +1,15 @@
1
  {
2
- "additional_special_tokens": [
3
- "<extra_id_0>",
4
- "<extra_id_1>",
5
- "<extra_id_2>",
6
- "<extra_id_3>",
7
- "<extra_id_4>",
8
- "<extra_id_5>",
9
- "<extra_id_6>",
10
- "<extra_id_7>",
11
- "<extra_id_8>",
12
- "<extra_id_9>",
13
- "<extra_id_10>",
14
- "<extra_id_11>",
15
- "<extra_id_12>",
16
- "<extra_id_13>",
17
- "<extra_id_14>",
18
- "<extra_id_15>",
19
- "<extra_id_16>",
20
- "<extra_id_17>",
21
- "<extra_id_18>",
22
- "<extra_id_19>",
23
- "<extra_id_20>",
24
- "<extra_id_21>",
25
- "<extra_id_22>",
26
- "<extra_id_23>",
27
- "<extra_id_24>",
28
- "<extra_id_25>",
29
- "<extra_id_26>",
30
- "<extra_id_27>",
31
- "<extra_id_28>",
32
- "<extra_id_29>",
33
- "<extra_id_30>",
34
- "<extra_id_31>",
35
- "<extra_id_32>",
36
- "<extra_id_33>",
37
- "<extra_id_34>",
38
- "<extra_id_35>",
39
- "<extra_id_36>",
40
- "<extra_id_37>",
41
- "<extra_id_38>",
42
- "<extra_id_39>",
43
- "<extra_id_40>",
44
- "<extra_id_41>",
45
- "<extra_id_42>",
46
- "<extra_id_43>",
47
- "<extra_id_44>",
48
- "<extra_id_45>",
49
- "<extra_id_46>",
50
- "<extra_id_47>",
51
- "<extra_id_48>",
52
- "<extra_id_49>",
53
- "<extra_id_50>",
54
- "<extra_id_51>",
55
- "<extra_id_52>",
56
- "<extra_id_53>",
57
- "<extra_id_54>",
58
- "<extra_id_55>",
59
- "<extra_id_56>",
60
- "<extra_id_57>",
61
- "<extra_id_58>",
62
- "<extra_id_59>",
63
- "<extra_id_60>",
64
- "<extra_id_61>",
65
- "<extra_id_62>",
66
- "<extra_id_63>",
67
- "<extra_id_64>",
68
- "<extra_id_65>",
69
- "<extra_id_66>",
70
- "<extra_id_67>",
71
- "<extra_id_68>",
72
- "<extra_id_69>",
73
- "<extra_id_70>",
74
- "<extra_id_71>",
75
- "<extra_id_72>",
76
- "<extra_id_73>",
77
- "<extra_id_74>",
78
- "<extra_id_75>",
79
- "<extra_id_76>",
80
- "<extra_id_77>",
81
- "<extra_id_78>",
82
- "<extra_id_79>",
83
- "<extra_id_80>",
84
- "<extra_id_81>",
85
- "<extra_id_82>",
86
- "<extra_id_83>",
87
- "<extra_id_84>",
88
- "<extra_id_85>",
89
- "<extra_id_86>",
90
- "<extra_id_87>",
91
- "<extra_id_88>",
92
- "<extra_id_89>",
93
- "<extra_id_90>",
94
- "<extra_id_91>",
95
- "<extra_id_92>",
96
- "<extra_id_93>",
97
- "<extra_id_94>",
98
- "<extra_id_95>",
99
- "<extra_id_96>",
100
- "<extra_id_97>",
101
- "<extra_id_98>",
102
- "<extra_id_99>"
103
- ],
104
  "eos_token": "</s>",
 
 
 
 
 
 
 
105
  "pad_token": "<pad>",
 
106
  "unk_token": "<unk>"
107
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
  "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
  "unk_token": "<unk>"
15
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,112 +1,15 @@
1
  {
2
- "additional_special_tokens": [
3
- "<extra_id_0>",
4
- "<extra_id_1>",
5
- "<extra_id_2>",
6
- "<extra_id_3>",
7
- "<extra_id_4>",
8
- "<extra_id_5>",
9
- "<extra_id_6>",
10
- "<extra_id_7>",
11
- "<extra_id_8>",
12
- "<extra_id_9>",
13
- "<extra_id_10>",
14
- "<extra_id_11>",
15
- "<extra_id_12>",
16
- "<extra_id_13>",
17
- "<extra_id_14>",
18
- "<extra_id_15>",
19
- "<extra_id_16>",
20
- "<extra_id_17>",
21
- "<extra_id_18>",
22
- "<extra_id_19>",
23
- "<extra_id_20>",
24
- "<extra_id_21>",
25
- "<extra_id_22>",
26
- "<extra_id_23>",
27
- "<extra_id_24>",
28
- "<extra_id_25>",
29
- "<extra_id_26>",
30
- "<extra_id_27>",
31
- "<extra_id_28>",
32
- "<extra_id_29>",
33
- "<extra_id_30>",
34
- "<extra_id_31>",
35
- "<extra_id_32>",
36
- "<extra_id_33>",
37
- "<extra_id_34>",
38
- "<extra_id_35>",
39
- "<extra_id_36>",
40
- "<extra_id_37>",
41
- "<extra_id_38>",
42
- "<extra_id_39>",
43
- "<extra_id_40>",
44
- "<extra_id_41>",
45
- "<extra_id_42>",
46
- "<extra_id_43>",
47
- "<extra_id_44>",
48
- "<extra_id_45>",
49
- "<extra_id_46>",
50
- "<extra_id_47>",
51
- "<extra_id_48>",
52
- "<extra_id_49>",
53
- "<extra_id_50>",
54
- "<extra_id_51>",
55
- "<extra_id_52>",
56
- "<extra_id_53>",
57
- "<extra_id_54>",
58
- "<extra_id_55>",
59
- "<extra_id_56>",
60
- "<extra_id_57>",
61
- "<extra_id_58>",
62
- "<extra_id_59>",
63
- "<extra_id_60>",
64
- "<extra_id_61>",
65
- "<extra_id_62>",
66
- "<extra_id_63>",
67
- "<extra_id_64>",
68
- "<extra_id_65>",
69
- "<extra_id_66>",
70
- "<extra_id_67>",
71
- "<extra_id_68>",
72
- "<extra_id_69>",
73
- "<extra_id_70>",
74
- "<extra_id_71>",
75
- "<extra_id_72>",
76
- "<extra_id_73>",
77
- "<extra_id_74>",
78
- "<extra_id_75>",
79
- "<extra_id_76>",
80
- "<extra_id_77>",
81
- "<extra_id_78>",
82
- "<extra_id_79>",
83
- "<extra_id_80>",
84
- "<extra_id_81>",
85
- "<extra_id_82>",
86
- "<extra_id_83>",
87
- "<extra_id_84>",
88
- "<extra_id_85>",
89
- "<extra_id_86>",
90
- "<extra_id_87>",
91
- "<extra_id_88>",
92
- "<extra_id_89>",
93
- "<extra_id_90>",
94
- "<extra_id_91>",
95
- "<extra_id_92>",
96
- "<extra_id_93>",
97
- "<extra_id_94>",
98
- "<extra_id_95>",
99
- "<extra_id_96>",
100
- "<extra_id_97>",
101
- "<extra_id_98>",
102
- "<extra_id_99>"
103
- ],
104
  "clean_up_tokenization_spaces": true,
 
105
  "eos_token": "</s>",
106
- "extra_ids": 100,
 
107
  "model_max_length": 512,
108
  "pad_token": "<pad>",
109
- "sp_model_kwargs": {},
110
- "tokenizer_class": "T5Tokenizer",
 
111
  "unk_token": "<unk>"
112
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
  "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
  "model_max_length": 512,
10
  "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
  "unk_token": "<unk>"
15
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:452f49e36c4ee4da22df18785fce140ea211e12d1f122f022b6925e80ef231e7
3
  size 4472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d559f5ea91d520f8f4d254b91aa7a740d3c91a634c874cae6174cbf4b21b6ef2
3
  size 4472
vocab.json ADDED
The diff for this file is too large to render. See raw diff